Highlights:

  • Administrators can use a centralized interface provided by Aruba Networking Central to keep an eye on the network infrastructure of their organizations.
  • The tool at the top of the UI employs AI to assist admins in finding other technical material and troubleshooting instructions.

HPE upgrades Aruba Networking Central, its cloud-based network management platform, with large language models to make administrators more productive.

Hewlett Packard Enterprise Co. recently announced the update. The models enhance the artificial intelligence elements already present on the platform, which make activities like troubleshooting broken switches easier.

Administrators can use a centralized interface provided by Aruba Networking Central to keep an eye on the network infrastructure of their organizations. The platform gathers information about switches, Wi-Fi access points in offices, and other devices. It also carries out a number of related duties: The platform allows administrators to configure networking hardware and troubleshoot issues.

The new LLMs that HPE unveiled are being made available for the search bar on Aruba Networking Central. Currently, the tool at the top of the UI employs AI to assist admins in finding other technical material and troubleshooting instructions. HPE claims that the search bar’s capabilities have been greatly increased by its new language models.

The LLMs make numerous enhancements to the tool with the goal of making it easier to use. The search bar can now comprehend questions that involve technical jargon connected to networking better, according to the business. A recently added autocomplete function makes several query suggestions based on the text the user has started typing. The enhanced search bar, according to HPE, returns results much more quickly than many commercial chatbots.

The tool can also summarize documentation for HPE’s Aruba networking equipment due to another new functionality. Based on the pertinent technical publications, the search bar can provide an administrator with natural language help when they ask questions about tasks like installing switches. Links to the original documents containing the material are included in every response.

One of the LLMs in the recent release, according to HPE, was trained to identify both corporate-identifiable information and personal data. Two tasks make use of the model. It first makes it possible for the search bar to comprehend searches that include company-specific data, such as the name of an office building. Secondly, it enables HPE to identify queries containing sensitive data and refrain from adding them to the training datasets for its LLMs.

The new LLMs, according to the company, were trained on a data repository ten times greater than those utilized by competitors. More than three million searches that users have typed into Aruba Networking Central’s search box are included in that collection. Tens of thousands of technical documents that HPE has made available to the public on its Aruba product line were also added.

HPE Executives Alan Ni and Karthik Ramaswamy reported, “We have implemented multiple locally trained and hosted LLMs to take advantage of the human understanding and generative qualities of GenAI without the risk of data leaks via external API queries to and from our data lake.”

Earlier this month, Aruba Networking Central users began to get access to the LLMs. By April, HPE hopes to have finished the rollout.